|Publication number||US6928500 B1|
|Application number||US 08/883,118|
|Publication date||Aug 9, 2005|
|Filing date||Jun 26, 1997|
|Priority date||Jun 29, 1990|
|Also published as||US7668997, US20050232287|
|Publication number||08883118, 883118, US 6928500 B1, US 6928500B1, US-B1-6928500, US6928500 B1, US6928500B1|
|Inventors||Raj Ramanujan, James B. Keller, William A. Samaras, John DeRosa, Robert E. Stewart|
|Original Assignee||Hewlett-Packard Development Company, L.P.|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (13), Non-Patent Citations (2), Referenced by (29), Classifications (16), Legal Events (6)|
|External Links: USPTO, USPTO Assignment, Espacenet|
This application is a continuation of application Ser. No. 08/047,164, filed on Apr. 12, 1993 now abandoned, which is a continuation of application Ser. No. 07/546,547, filed on Jun. 29, 1990, now abandoned.
This invention relates to computer systems that have more than one processor that share a memory. More specifically, the present invention relates to bus arrangements for a shared memory of a multiprocessor computer system.
The conventional approach to buses in computer systems in which the same information was transmitted to, and received from, a plurality of system elements, such as CPUs, memories, or the like, was to use a multi-drop bus. A typical multi-drop bus consists of a number of bus wires that run to each element.
A beneficial aspect of a multi-drop bus is that only one bus element, such as a CPU, is allowed to transmit on the bus at a time and all bus elements can see what is being transmitted on the bus.
A drawback of the multi-drop bus is that all of the bus elements are always connected to the bus and the control of arbitration for access to the bus is predicated on separate communications between a bus element and other bus elements. This takes time and, therefore, slows down the processing speed of the system.
While multi-drop buses work well for many systems, as processing speeds increase, these bus systems have problems. These problems are a direct result of the plurality of bus elements being coupled to the same line.
In particular, devices based on ECL logic have experienced substantial problems with multi-drop bus systems. These problems have prevented such ECL based systems from operating at design speed. The result, therefore, was that in a high speed system, buses operated at a much slower speed that negated the processing speed advance endemic in these systems.
Hence, there is a need for a bus that can be used in a multiprocessor environment with a shared memory which operates at high speed, with logic such as ECL logic.
The present invention is a bus system that may be used in high speed computing systems.
The high speed bus system of the present invention provides much of the functionality familiar from conventional multi-drop buses, such as common visibility of each transaction by all CPUs, but with the speed and signal quality advantages of unidirectional point-to-point buses. This invention accomplishes this object through use of gates or multiplexers, and logic to control them, as described hereinafter, in place of the multi-drop bus. A particular embodiment of this invention allows the information seen by the memory to be only that which is needed by the memory, while still allowing all the CPUs to see all the information they need.
The high speed bus system of the present invention is preferably used in a multi-processor, shared memory system and is disposed between the plurality of processors and a memory array, referred to as a shared memory. The high speed bus system carries commands and data from the processors to the memory array, from memory array to the processors, and from one processor to the other processors.
The high speed bus system of the present invention includes a central unit and a series of unidirectional buses. A pair of uni-directional buses are connected between the central unit and the memory array. The first uni-directional bus is for transmissions from the central unit to the shared memory. The second uni-directional bus is for transmissions from the shared memory to the central unit.
There are also uni-directional buses for transmissions between the plurality of processors and the central unit. Each processor has two point-to-point uni-directional buses that connect to the central unit. One of the buses is from transmissions from the processor to the central unit and the other is for transmissions from the central unit to the processor.
The central unit receives all of the transmissions from the plurality of processors for input to the shared memory and all of the transmissions from the shared memory for the processors, and appropriately distributes these transmissions. The central unit also controls the shared buses of the high speed bus system so that only one processor at a time may have access to the shared buses. The shared use of these buses is determined by the arbitration logic that is part of the central unit.
A first embodiment of the central unit includes a series of OR gates for receiving transmissions from the processors over the point-to-point uni-directional buses, and for receiving transmissions from the memory controller. The OR gates process the transmissions from processors by distributing them to the memory controller and the other processors. These gates process the transmissions from the memory control by distributing them to the processors. The memory controller controls all of the transmissions between the processors and the shared memory. The memory controller also includes arbitration logic.
The first embodiment also includes a state device at the output of the series of OR gates that controls the transmissions from a processor to the other processors and from the shared memory to the processors. The transmissions output from the state device are processed by the driver before being placed on the point-to-point buses to the processors.
The second embodiment of the central unit is similar to the first embodiment except that the series of OR gates is replaced with a series of multiplexers and a logic element is added to control the multiplexers. The first multiplexer of the series has logic associated with its input to assist in the keeping the shared bus full, as well as determining the validity of commands and data from the processors.
The high speed bus system of the present invention provides a high speed bus for use in transmitting commands and data between the processors and a shared memory in a multi-processor, shared memory system.
Each of the CPUs is connected to the central unit 15 over a point to point bus. Accordingly, E-BUS 0 TA bus 17 connects CPU 0 at 11 to central unit 15, E-BUS 1 TA bus 19 connects CPU 1 at 13 to central unit 15, E-BUS 2 TA bus 18 connects CPU 2 at 12 to central unit 15, and E-BUS 3 TA bus 20 connects CPU 3 at 14 to central unit 15 (collectively, “E-BUS TA buses”). These uni-directional buses are for transmissions from the CPUs to central unit 15. For the transmission of data from central unit 15 to the CPUs, there are E-BUS 0 FA bus 21, which connects CPU 0 at 11 to the central unit, E-BUS 1 FA bus 23, which connects CPU 1 at 13 to the central unit, E-BUS 2 FA bus 22, which connects CPU 2 at 12 to the central unit, and E-BUS 3 FA bus 24, which connects CPU 3 at 14 to central unit.
Each of the CPUs also connect to an I/O bus adaptor 25 over two uni-directional buses. Each is a 16-bit bus. One bus is an input bus and the other is an output bus.
As shown in
Central unit 15 is connected to shared memory 31 by uni-directional A-BUS FA 33 and uni-directional bus A-BUS TA 35. A-BUS FA 33 is for transmissions from the central unit to the shared memory 31. Conversely, A-BUS TA 35 is for transmissions from shared memory 31 to the central unit.
Shared memory 31 includes memory modules which are designated 3 la, 31 b, 31 c, 31 d, 31 e, and 31 f. Each memory module connects to central unit 15 via A-BUS FA at 33 and A-BUS TA at 35. It is to be understood that there may be more shared memory, or there may be more or less memory modules for a single shared memory and still be within the scope of the invention. It is further understood that each module may be of the same type of memory or each may be of a different type.
E-BUS TA buses 17, 19, 18, and 20, E-BUS FA buses 21, 23, 22, and 24, and A-BUS FA bus 33 are 32-bit parallel buses, and A-BUS TA bus 35 is a 64-bit parallel bus.
The central unit 15 performs two basic functions. First, it combines the signals input to it from the CPU and memory on the E-BUS TA and A-BUS TA buses, respectively, so that they are provided as outputs on the output buses E-BUS FA and A-BUS FA. Second, it contains a memory controller for memory modules 31 a–31 f. Central unit 15 also controls system timing. This is done through a central clock which is not shown.
As shown in
According to this first implementation, E-BUS 0 TA 17 from CPU 0 at 11 connects to a first input to OR gate 37, E-BUS 1 TA bus 19 from CPU 1 at 13 connects to the second input to gate 37, E-BUS 2 TA bus 18 from CPU 2 at 12 connects to the third input of OR gate 37, and E-BUS 3 TA bus 20 from CPU 3 at 14 connects to the fourth input to OR gate 37. The output of OR gate 37 is bus 36 which is the first input to OR gate 41. Bus 36 is also input to memory controller 45. The second input to OR gate 41 is the output from memory controller 45. The output of OR gate 41 on bus 39 is input to the data input of state device 42. When state device 42 receives the input from OR gate 41, it stores the output for one cycle before providing it at its output.
Although not shown, conventional arbitration logic and communication between the CPUs exist. This arbitration logic, which can be centrally located or in one or more of the CPUs is necessary to ensure that only one of the CPUs has access to the bus 36 at a time. This logic functions on a request/request granted type of operation.
The output of state device 42, after passing through driver 43, is input to CPU 0 at 11, CPU 1 at 13, CPU 2 at 12, and CPU 3 at 14 via E-BUS 0 FA bus 21, E-BUS 1 FA bus 23, E-BUS 2 FA bus 22, and E-BUS 3 FA bus 24, respectively. It is understood that the output to the state device is a 32-bit wide output.
Notice that anything applied on the E-BUS x TA buses (where “x” represents any of the bus elements) will show up in the next bus cycle on the E-BUS x FA buses. Therefore, arbitration for the E-BUS x FA buses must be done prior to any element transmitting on the E-BUS x TA buses.
As stated, the output of OR gate 37, bus 36, is input to the memory controller 45. The second input to OR gate 41 is the output of memory controller 45. Therefore, the refill data from memory 31 that is on the A-BUS TA bus 35 passes through memory controller 45 for input to the second input of OR gate 41. This data is later caused to be input to state device 42. After processing by the state device, the refill data is supplied to the CPUs via driver 43 and the E-BUS FA buses. This is how refill data operates for a read.
When it is necessary to write data to the memory, data from OR gate 37 on line 36 is coupled through memory controller 45 onto the A-BUS FA 33. No refill data is provided because the data is written to memory.
Port logic 49 is disposed at the input to MUX 37 a. The buffer in port logic 49 can hold up to three words, the number of words being a function of the length of time for the CPU's to recognize a bus grant condition from one of the E-BUS TA buses.
Although most of the signals from the E-BUS TA buses are poised ready for input to MUX 37 a, there are certain bits from port logic 49 for output to logic element 50. Logic element 50 processes these bits and provides selection inputs to MUXes 37 a and 41 a.
Other logic included in the logic 50 of
Again referring to
Four types of information may be communicated on the E-BUS TA buses. These (1) data, commands and address information (“DAL”); (2) function code (FC) information, which are signals to indicate whether the information on the DAL lines is a command, or address or data; (3) “snoopy hit” information, which indicates that a CPU associated with that bus has a “snoopy hit,” and (4) parity information.
Although not shown, each of the CPUs may include a cache memory. These memories may be used to speed up access to data which is being used extensively by a CPU. Thus, each time a read command is sent out, each CPU checks to see if the associated address is in its cache. In a manner that will be explained in more detail below, this operation which is known as a “snoopy” operation, is done with timing that insures that any response to a “snoopy” read, which is a “snoopy hit,” takes place before refill data returns from one of the memory modules in memory 31.
Again referring to
The output of the state device 53 is also input to validity logic 57. The second input to validity logic 57 is a signal that is fed back from the output of validity logic 57. The other output of validity logic 57 connects to the selection inputs of MUX 59. The PORT GRANT signal on line 61, which is output from arbitrator 51, is also input to validity logic 57.
The function of validity logic 57 is to determine if commands and data are valid, and which of the data, either in buffer 55 or input directly to port MUX 59, are to be switched onto bus 63 at the output port MUX 59.
The output of port MUX 59 on bus 63 is input to MUX 37 a. The output of port MUX 59 on bus 63 is also input to port select logic 65. MUX 37 a and port select logic 65 are part of scheduling logic 66.
Port select logic 65, in response to outputs from the arbitrator 51, selects one of the four inputs to MUX 37 a to be coupled to the output of that MUX. This is coordinated with the operation of validity logic 57 which controls the output of port MUX 59 on bus 63. Port select logic 65 grants the four ports supplying inputs to bus 63 access to bus 36 on a round robin basis.
Output bus 36 is input to resource check logic block 67 of the arbitrator 51, MUX 41 a, and a number of other units. These units are memory map unit (“MMAP”) 69, lock logic unit (“LOCK”) 71, input/output unit (“CPIO”) 73, interrupt request unit (“IREQ/SNIT”) 75, memory controller (“MEMC/DBEC”) 77, and memory write data path unit (“MWDP”) 79. Each of the units 69, 71, 73, 75, and 77 also provide inputs to the MUX 41 a.
Resource check 67 receives status inputs from MMAP 69, LOCK 71, CPIO 73, IREQ/SNIT 75, MEMC/DBEC memory controller 77, and MWDP 79. These are the memory module status, the lock register status, the I/O module status, the error status, the memory controller status, and the write buffer status messages. In addition, the resource check logic block 67 generates ARB commands for input to the MUX 41 a and a ARB MUX SELECT command for selecting which input will be output from MUX 41 a for input to state device 42.
A-BUS TA 35 is a 64-bits wide bus. The signals on that bus include DAL information, ECC (error correction code) information, and ACK (acknowledgement) information. The ACK bit is processed by memory read data path (“MRDP”) 81. The output of MRDP 81 which includes the DAL and ECC information is input to MEMC/DBEC 77. The DAL information here is generally refill data. The output of MEMC/DBEC is the refill data and this output is one of the inputs to MUX 41 a.
MEMC/DBEC 77 also provides an output on A-BUS FA bus 33. This output includes the DAL, ECC, FC, and parity information. This information on A-BUS FA bus 33 is input to memory modules 31 a–31 f. The output of MUX 41 a through the state device 42 includes the same information that MEMC/DBEC 77 put on A-BUS FA 33 except that the ECC information is not included.
When the appropriate command signal on bus 36 is input to resource check logic 67, the resource check logic uses the status information input from MMAP 69, LOCK 71, CPIO 73, IREQ/SNIT 75, MEMC/DBEC 77, and MWDP 79 to arbitrate between the different inputs to determine which input will be given access to E-BUS FA buses 21–24 through MUX 41 a and state machine 42. The signals that desire access to these buses are the RSCK DAL and RSCK FC signals on bus 36, MMAP LW RD DAL signal output from MMAP 69, LOCK LW RD DAL signal output from LOCK 71, the CPIO LW RD DAL signal output from CPIO 73, the IREQ/SNIT LW RD DAL output from IREQ/SNIT 75, and the METL REFILL DAL signal output from MEMC/DBEC 77. Resource check logic 67 controls access to these buses via the output lines coupled through state devices 67 a and 67 b and the ARB MUX SELECT signal output from resource check logic 67.
The outputs from state device 67 a on line 61 and 85 are for controlling access of E-BUS TA bus information onto bus 36. The outputs from state device 67 b on lines 83 are for causing selected DAL information from MMAP 69, LOCK 71, CPIO 73, IREQ/SNIT 75, and MEMC/DBEC 77 to be input to MUX 41 a.
Lines 96 of bus 63 carry the DAL and FC signals. These signals are the inputs to MUX 37 a. The FC lines signals are also input to OLD FC MUX 95.
Lines 97 of bus 63 carry the port CMD VALID signals. These signals are inputs to barrel shifter 99. The output of barrel shifter 99 is input to priority encoder 401. The 4-bit output of priority encoder 401 is one of the inputs to MUX 403. This 4-bit output is also input to left shift one block 405. The output of left shift one block 405 is one of the inputs to MUX 407. MUX 407 has state device 409 disposed at its output. The output of state device 409 feeds back as the second 4-bit input to the MUX 407 and as a 4-bit control input to barrel shifter 99.
The first 4-bit input to MUX 403 is a feed back signal from state device 411. This is the last input to MUX 403. The 4-bit output of MUX 403 is input to state device 411. The cycle after the output from MUX 403 is input to state device 411, it is provided at the output of the state device. The 4-bit output of state device 411 is also input to the selection inputs of OLD FC MUX 95 which has as inputs the FC signals from lines 96 of bus 63.
The output of MUX 95 on line 419 is the OLD FC signal. This is an input to port select generator 93 along with the output of OR gate 91 and two other inputs. These two other inputs are the SCHD GRANT signal on line 85 a and SNOOPY HIT SHADOW signal on line 85 b. Both of these signals are output from state device 67 a of arbitrator 51. These signals are for controlling access of the E-BUS TA buses to bus 36.
The first output of port select generator 93 is the selection input of MUX 403. The second output is input to the selection input of MUX 407. The control of these two MUXes determines the content of the output from MUX 37 a on bus 36 and what the 4-bit SCHD ID signal on line 86 will be. The output of MUX 403 is input to the selection input of MUX 37 a whose output is bus 36.
Assuming that all four ports have valid commands, priority encoder 401 prioritizes the ports with the highest priority being output first from the priority encoder on line 413 as the “current port” signal. This is also input to left shift one block 405. The output of the left shift one block is the next port in the sequence. So, the output of the left shift one block is the “next port” signal, which is input to MUX 407. The other input to MUX 407 through state device 409 is a feed back signal. This signal also connects to the control inputs to barrel shifter 99. Hence, the signal will cause the barrel shifter to point to the port associated with this signal. The signal that usually is at the feed back loop is the “current port”. This is true until changed by the selection of the “next port”.
As an example, assume that the priority encoder 401 determines that port “0” should have access to bus 36 first. The 4-bit output of priority encoder 401 is input to left shift one block 405 and, as such, will shift left shift one block to indicate the next port which according to a normal sequence would be port “1.”
The output of left shift one block 405 is loaded into the second input to a MUX 407. The first input to MUX 407 is the current port, which is port “0,” and is the present output of MUX 407 and latched in state device 409. This signal is fed back to an input of MUX 407. The state device continues to feed back port “0” until the port “0” information has been fully transmitted. This is controlled by port select generator 93 continuing to select the feed back input until port “0” has completed placing its data on bus 36.
When port “0” has completed its transmission, port select generator 93 selects the second input to MUX 407 which is the output of left shift one block 405. This will now provide the “next port,” port “1,” at the output of MUX 407. On the next cycle, the “next port” signal will be output from state device 409 and fed back to the first input to MUX 407.
When this value designating port 1 is output from state device 409, it is also input to the barrel shifter 99. The new port designation signal advances the barrel shifter by one, so long as the “next port” in the normal sequence order has a valid port CMD VALID signal. If the next port in sequence is not valid, the barrel shifter advances to the next valid port.
The output of the barrel shifter 99 is input to priority encoder 401 which now provides an output representative of the new port. As such, the newly selected port becomes the “current port” and a new “next port” is selected in the above described manner. This method of operation would continue with each port having its turn in round robin fashion.
The output from port select generator 93 that is input to the selection input of MUX 403, usually selects the “current port” input for output from that MUX. This “current port” output will select its signals for output from MUX 37 a on bus 36. It is only when other events take place that the other inputs to MUX 403 are selected for output as will be described.
Now that the method by which a port is given access to bus 36 has been described, the operation of scheduling logic 66 will be discussed.
Each command is usually followed by at least one word. This word may be an address, or data (in the case of a refill). This address or data may be followed by additional data (in the case of a write command), a refill command, or a SWAP command (a combined read and write command).
Once a port is given access to the bus, it must continue to be given access until it is finished transmitting its commands or data onto bus 36. For example, in the case of a SWAP command, the port must have continuous access to send the SWAP command, a read address, a write back command, a write address, and then the write data. During the time that the data and commands are being sent, FC changes states according to what is on the DAL lines. If it is a command, it has one state and the other state if it is not a command.
The purpose of the MUX 403 is to select between a “previous port”, a “snoopy port”, and the “current port”. As stated, it is only when predetermined events take place that the “previous port” or “snoopy port” inputs to MUX 403 are selected. The method of selecting the output of MUX 403 will now be discussed.
The output of MUX 403 is input to the selection inputs of MUX 37 a. This determines which port is granted access to bus 36. Normally, the output of MUX 403 is the “current port”; hence the “current port” is selected at MUX 37 a. The “current port” is also input to state device 411. On the clock cycle after the “current port” is input state device 411, with the output therefrom on line 417. This output is input to the selection inputs of OLD FC MUX 95 and fed back as the “previous port” put to MUX 403.
After passage of one cycle, the information being transmitted on the port selected at MUX 37 a is data or addresses, and not a command. Accordingly, the FC signal will change states. This new state will be input to port select generator 93. This will cause the SCHD MODE SELECT (scheduling mode selector) output of the generator to have a bit pattern that will select the “previous port” input to MUX 403 which is latched in state device 411. The “previous port” value will remain as the output of MUX 403 until the state of the FC signal on line 419 changes signifying the end of data and the presence of a new command. It is only then that port select generator 93 will change its selection signals to select the “current port” rather than the “previous port.” This action ensures that data transmission in complete before another command is placed on bus 36.
In the meantime, in response to the change in state of the FC signal on line 419, the “next port” value is selected at MUX 407. This is done by port select generator 93 changing which output the selection signals selects to be output from MUX 407. Once selected, the “next port” signal, through state device 409, is fed back to MUX 407 and barrel shifter 99. Barrel shifter 99 then selects the next valid port, which now becomes the “current port” on line 413. The scheduling logic 66 now awaits the next change in the state of the selected FC signal for repeating these actions. As an example of the operation of scheduling logic 66, the following is provided.
During normal operations, without a “snoopy hit,” when the “current port”, e.g., port “0”, is selected and coupled through MUX 403, this “current port” signal makes the selection of the “current port” DAL and FC at MUX 37 a. On the next clock cycle, this port designation, i.e., port “0”, is available at the output of state device 411. The output of state device 411 selects the corresponding port FC signal to be output from MUX 95. Thus, if port “0” is the current port, the FC bit for port “0” will be output from MUX 95 and fed back to port select generator 93.
During the first cycle, which contained a command, the FC bit, for example, may be a logic “1” value. On the second cycle, when other than a command is transmitted, it will change to a logic “0” value.
When the port “0” FC signal switches, this changed value is input to port select generator 93. In response to this change, port select generator 93 will select the “previous port” input that is output from state device 411. Hence, the output of MUX 403 is the “previous port” input. This all results in a holding period so that all of the port “0” information can be transmitted. Once the FC signal changes states to indicate that a command is again being transmitted, the output from port select generator 93 to the selection inputs of MUX 403 will again select the “current port” input, which now is port “1”. The process repeats itself for each of the ports taken in round robin fashion.
The remaining portions to be discussed regarding
“Snoopy hits” are given priority over normal commands and data. Accordingly, the SNOOPY HIT SHADOW signal, when it has the proper state, will prevent any commands or data from being placed on bus 36.
A “snoopy hit shadow” is a time which covers the period required to obtain signals back from the CPUs when there has been a “snoopy hit”. That is, once a read command is put out on the bus, there is a certain amount of time before a signal will come back indicating a “snoopy hit”, i.e., the requested data is in a CPU cache. If there is a “snoopy hit”, a “snoopy refill command” will occur so the identified data may be provided.
Once a read command is issued and detected in command decoder 435, a “snoopy shadow” period is started. One of the outputs of command and resource check 427 is the “snoopy shadow start” signal on line 425. This signal is input to multistage shift register 429. The outputs of shift register 429 are combined in OR gate 431. The output of OR gate 431 is fed back to the command and resource check 427 and also is output from resource check logic 67 on line 85 b as the SNOOPY HIT SHADOW signal.
Again referring to
If there are more than one “snoopy hit”, priority encoder 89 outputs a signal indicative of the “snoopy” port that has been assigned the highest priority.
When there has been a “snoopy hit” identified, the output of OR gate 91 will change state. In response to the change of state of the OR gate 91 output, port select generator 93 now selects the correct “snoopy” port for access to the bus 36 through MUX 403 and MUX 37 a. That is, the “snoopy port” output from priority encoder 89 will be coupled to the output of MUX 403. This output will select the port corresponding to the correct “snoopy hit” for output through MUX 37 a. The selected “snoopy port” will then send out its refill data on bus 36.
Again referring to
As indicated in
The nature of the memory control is to control a number of commands that are pending at one time, and yet allow only one command pending for any given memory module. To achieve this preferred type of memory control, command and resource check 427 decodes commands and their associated addresses to determine if it can grant the port requesting access, access to the memory bus based on the number of commands then pending and the availability of a specific memory module.
Again referring to
For the purposes of discussing selection of the output of MUX 41 a, it is understood that if MEMC/DBEC 77 is providing refill data, then none of the ports can be granted access to the bus via MUX 41 a. Thus, during the transfer of refill data through the MUX 41 a, line 61 and 85 are controlled to ensure that all of the refill data is put onto the E-BUS FA buses 21–24 before a port is given access.
The following are examples of processing commands and data according to the system and method of the present invention and, in particular, according to the system shown in
If one of a number of CPUs wants access to the bus 36, it sends out a command followed by an address in two successive cycles. This command and address will be on E-BUS TA buses 17–20.
There are basic commands which involve memory transfers. These are the read commands, write back commands in which data is written from one CPU to memory, refill commands in which data is written to one CPU from either memory or another CPU, and SWAP command. These commands will be described in conjunction with the appropriate Figures.
If the command is valid, as determined by validity logic 57, and the requested memory module is available, at the third cycle, the CPU 1 port is granted access to bus 36 as shown at 107 of
During the next cycle, the address from the second buffer location of buffer 55 in port logic 49 is put on bus 36 as indicated at 111. The read command at 101, which the CPU put on one of the E-BUS TA buses during the first cycle, appears on each of the E-BUS FA buses 21–24 during the third cycle. In this way, the CPU which sent the original command will know, as will all of the other CPUs, that the request has been granted and that the requesting CPU has been given access to bus 36. This is done without the necessity of making a separate communication to each CPU. Also, the read command and address at 101 and 103, respectively, are provided to each of the other CPUs so that they may determine if they have the requested information in their caches for the purpose of a “snoopy hits.”
If it is a write command, the first piece of data is sent on a third cycle. The remainder of the data is provided in subsequent cycles. The write command and address will be processed in the same manner as a read command and address. The data, however, will be written to memory and not returned.
Starting with the first cycle shown in
As an example, assume bus 36 was busy when refill command 201 was sent from CPU 3 at 14. As a result, CPU 3 at 14 will have to wait for access to the bus. Accordingly, the refill command, data “0”, and data “1”, are sent and held in the buffer 55 in port logic 49, as stated, until access is granted. This buffer of port logic 49, as stated, can hold 3 words.
Because the bus was busy, the earliest times at which arbitration can take place is at the fourth cycle. Thus, CPU 3 was given access to the bus 36 two cycles after it asked for it (two cycles late).
In the meantime, at the fourth cycle, the third piece of refill data “2” as 207 has been placed on the bus and is held in state device 53 (
At the fifth cycle, the refill command is latched in state device 42. This refill command, indicated at 209, is transferred from the first buffer location. Similarly, the refill data “0” at 211 is transferred from the second buffer location in buffer 55 and the refill data “1” at 213 is transferred from the third buffer location. At the seventh cycle, the refill data “2” is transferred into the state device 42. It, therefore, is ready for output on the E-BUS FA at the next cycle, as shown at 215.
During the fourth cycle at 206, when arbitrator 51 granted the port access to the bus via line 61, validity logic 57 (see
The CPU that sent the refill command and refill data knows to begin sending data again beginning at seventh cycle, as indicated by refill data 217. The refill command was placed on E-BUS FA buses 21–24 at the fifth cycle, as indicated at 209. During the sixth cycle, the CPU 3 read this data and at seventh cycle began sending data again. Now, the two late cycle problem has been corrected. This is why refill data 2 at 207 appears 3 bytes long instead of one byte. This data at 271 appears on the bus 36 just after data 215 as shown. The remaining refill data is passed through without the use of the buffer. The use of the buffer and the bus system of the present invention assures that, once the bus is granted to a CPU, there is a continuous flow of data and commands.
This diagram shows a one cycle late arbitration. On the cycle after arbitration, the SWAP command appears on the E-BUS FA buses 21–24 at 311 followed by the read address at 313. Similar to the situation in
Data does not appear on the E-BUS FA buses. This is because the data is being written to memory. Accordingly, the data is coupled from bus 36 directly into the memory controller 45, and it is not coupled through MUX 41 a and state device 42 onto the E-BUS FA buses 21–24.
The terms and expressions that are used herein are used as terms of expression and not of limitation. And there is no intention in the use of such terms and expressions of excluding the equivalents of the features shown and described, or portions thereof, it being recognized that modifications are possible in the scope of the invention.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US4096572 *||Sep 28, 1976||Jun 20, 1978||Tokyo Shibaura Electric Co., Ltd.||Computer system with a memory access arbitrator|
|US4470114 *||Mar 1, 1982||Sep 4, 1984||Burroughs Corporation||High speed interconnection network for a cluster of processors|
|US4570220 *||Nov 25, 1983||Feb 11, 1986||Intel Corporation||High speed parallel bus and data transfer method|
|US4591979 *||Aug 25, 1983||May 27, 1986||Nec Corporation||Data-flow-type digital processing apparatus|
|US4737932 *||Jun 4, 1985||Apr 12, 1988||Nec Corporation||Processor|
|US4807184 *||Aug 11, 1986||Feb 21, 1989||Ltv Aerospace||Modular multiple processor architecture using distributed cross-point switch|
|US4834483 *||May 6, 1987||May 30, 1989||Bell Communications Research, Inc.||Fast optical cross-connect for parallel processing computers|
|US4837682 *||Apr 7, 1987||Jun 6, 1989||Glen Culler & Associates||Bus arbitration system and method|
|US4991084 *||Feb 5, 1988||Feb 5, 1991||International Business Machines Corporation||N×M round robin order arbitrating switching matrix system|
|US5072363 *||Dec 22, 1989||Dec 10, 1991||Harris Corporation||Multimode resource arbiter providing round robin arbitration or a modified priority arbitration|
|US5088024 *||Jan 31, 1989||Feb 11, 1992||Wisconsin Alumni Research Foundation||Round-robin protocol method for arbitrating access to a shared bus arbitration providing preference to lower priority units after bus access by a higher priority unit|
|US5168547 *||Jun 11, 1990||Dec 1, 1992||Supercomputer Systems Limited Partnership||Distributed architecture for input/output for a multiprocessor system|
|WO1987004826A1||Jan 27, 1987||Aug 13, 1987||Eastman Kodak Company||Multi-processor apparatus|
|1||*||"A SoC communication architecture with fine-grained control over bandwidths and latencies" By Xu, Ningyi; Liu Hong; Zhou Zucheng; Peng Jihu (abstract only) Publication Date: Oct. 21-24, 2003.|
|2||*||"Evaluation of reservation-arbitrated access schemes for statistical multiplexing of variable-bit-rate video traffic over dual bus metropolitan area networks" by Chan, H.C.B.; Leung, V.C.M. (abstract only) Publication Date: Jun. 1998.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US7133950 *||May 26, 2004||Nov 7, 2006||Sun Microsystems, Inc.||Request arbitration in multi-core processor|
|US7562171 *||Jul 14, 2009||International Business Machines Corporation||Method for interfacing components of a computing system with a pair of unidirectional, point-to-point buses|
|US7568060 *||Dec 15, 2005||Jul 28, 2009||International Business Machines Corporation||Method and system for interfacing components of a computing system with a pair of unidirectional, point-to-point buses|
|US7574582 *||Jan 26, 2004||Aug 11, 2009||Picochip Designs Limited||Processor array including delay elements associated with primary bus nodes|
|US7640387 *||Dec 29, 2009||Intel Corporation||Method and apparatus for implementing heterogeneous interconnects|
|US7668997||Jun 14, 2005||Feb 23, 2010||Hewlett-Packard Development Company, L.P.||High speed bus system that incorporates uni-directional point-to-point buses|
|US7917675 *||Mar 29, 2011||Rockwell Automation Technologies, Inc.||Method and apparatus for interconnecting modules|
|US8327113||Dec 4, 2012||Intel Corporation||Method, system, and apparatus for dynamic reconfiguration of resources|
|US8463312||Jun 11, 2013||Mindspeed Technologies U.K., Limited||Method and device in a communication network|
|US8559998||Nov 4, 2008||Oct 15, 2013||Mindspeed Technologies U.K., Limited||Power control|
|US8606934 *||Jan 5, 2009||Dec 10, 2013||Intel Corporation||Method, system, and apparatus for system level initialization by conveying capabilities and identifiers of components|
|US8712469||May 15, 2012||Apr 29, 2014||Mindspeed Technologies U.K., Limited||Accessing a base station|
|US8798630||Apr 4, 2012||Aug 5, 2014||Intel Corporation||Femtocell base station|
|US8849340||Apr 16, 2013||Sep 30, 2014||Intel Corporation||Methods and devices for reducing interference in an uplink|
|US8862076||Feb 22, 2013||Oct 14, 2014||Intel Corporation||Method and device in a communication network|
|US8892154||May 31, 2013||Nov 18, 2014||Intel Corporation||Method and device in a communication network|
|US8904148||Jul 5, 2011||Dec 2, 2014||Intel Corporation||Processor architecture with switch matrices for transferring data along buses|
|US9042434||Apr 4, 2012||May 26, 2015||Intel Corporation||Filter|
|US9107136||Feb 15, 2013||Aug 11, 2015||Intel Corporation||Femtocell access control|
|US9223738||Nov 2, 2012||Dec 29, 2015||Intel Corporation||Method, system, and apparatus for dynamic reconfiguration of resources|
|US20050060457 *||May 26, 2004||Mar 17, 2005||Sun Microsystems, Inc.||Cache crossbar arbitration|
|US20050232287 *||Jun 14, 2005||Oct 20, 2005||Hewlett-Packard Development Company, L.P.||High speed bus system that incorporates uni-directional point-to-point buses|
|US20060155956 *||Jan 26, 2004||Jul 13, 2006||Nolan John M||Processor array|
|US20070143511 *||Dec 15, 2005||Jun 21, 2007||International Business Machines Corporation||Method and system for interfacing components of a computing system with a pair of unidirectional, point-to-point buses|
|US20070300000 *||Sep 12, 2007||Dec 27, 2007||International Business Machines Corporation||Method for interfacing components of a computing system with a pair of unidirectional, point-to-point buses|
|US20080250168 *||Mar 31, 2008||Oct 9, 2008||Intel Corporation||Method and apparatus for implementing heterogeneous interconnects|
|US20090024715 *||Sep 23, 2008||Jan 22, 2009||Mani Ayyar||Method, System, and Apparatus for Dynamic Reconfiguration of Resources|
|US20090198348 *||Jan 29, 2009||Aug 6, 2009||Kenneth John Murphy||Method and Apparatus for Interconnecting Modules|
|US20090265472 *||Jan 5, 2009||Oct 22, 2009||Mani Ayyar||Method, System, and Apparatus for System Level Initialization|
|U.S. Classification||710/107, 710/240, 710/112, 710/305|
|International Classification||H04L12/403, H04L12/28, G06F15/173, G06F15/167|
|Cooperative Classification||H04L12/4625, H04L12/403, G06F15/167, G06F15/173|
|European Classification||H04L12/46B7B, H04L12/403, G06F15/173, G06F15/167|
|Dec 12, 2005||AS||Assignment|
Owner name: COMPAQ COMPUTER CORPORATION, TEXAS
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:DIGITAL EQUIPMENT CORPORATION;REEL/FRAME:016883/0031
Effective date: 19991230
Owner name: COMPAQ INFORMATION TECHNOLOGIES GROUP, L.P., TEXAS
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:COMPAQ COMPUTER CORPORATION;REEL/FRAME:016883/0035
Effective date: 20010620
Owner name: DIGITAL EQUIPMENT CORPORATION, MASSACHUSETTS
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:RAMANUJAN, RAJ K.;KELLER, JAMES B.;SAMARAS, WILLIAM A.;AND OTHERS;REEL/FRAME:016871/0969;SIGNING DATES FROM 19890809 TO 19900829
Owner name: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P., TEXAS
Free format text: CHANGE OF NAME;ASSIGNOR:COMPAQ INFORMATION TECHNOLOGIES GROUP, L.P.;REEL/FRAME:016883/0043
Effective date: 20021001
|Feb 9, 2009||FPAY||Fee payment|
Year of fee payment: 4
|Aug 11, 2009||CC||Certificate of correction|
|Mar 25, 2013||REMI||Maintenance fee reminder mailed|
|Aug 9, 2013||LAPS||Lapse for failure to pay maintenance fees|
|Oct 1, 2013||FP||Expired due to failure to pay maintenance fee|
Effective date: 20130809